Borrowing it
Nothing to install: this file belongs to Kemetra/Seshat-BI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/dbt-transformation-adapter/SKILL.mdgit clone --depth 1 https://github.com/Kemetra/Seshat-BIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kemetra/seshat-bi/dbt-transformation-adapter)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/dbt-transformation-adapter"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/dbt-transformation-adapter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/dbt-transformation-adapter"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/dbt-transformation-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00142 | $0.02398 |
| Opus 5 | $0.00071 | $0.01199 |
| Sonnet 5 | $0.00028 | $0.00480 |
| Haiku 4.5 | $0.00014 | $0.00240 |
Grade A, and why
dbt-transformation-adapter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt-transformation-adapter
- Authority category (F024): Execution Adapter /
DB-connected(NOT publish-capable). - Roadmap feature: F029 On-disk spec:
specs/023-dbt-transformation-adapter.
dbt is the build ENGINE: it compiles SQL, materializes models, and runs tests. Seshat BI
is the brain: it owns the approved source-map, the metric contracts, and the readiness
spine, and routes every judgment call to a named human. This skill is how the agent runs
dbt without letting it become the brain. You (the agent reading this) ARE the runtime; this
skill is procedure, not an engine -- there is no daemon, no scheduler, no auto-approver.
See docs/decisions/0009-dbt-is-transformation-adapter.md and
templates/dbt-adapter-contract.md.
ACTIVATED: feature 133 added the governed runtime under
dbt/, the pinneddbt-core==1.12.0+dbt-postgres==1.10.2extra, and theseshat dbtcommand family. Use that wrapper only; raw dbt commands bypass the accepted-plan, selector, shadow-schema, redaction, lock, and evidence contracts.
Scope boundary (read first)
Invoke-and-record only. This skill runs dbt behind the gate and records its findings as
evidence; it does NOT define source mapping, metric contracts, or semantic logic, does NOT
publish Power BI, and does NOT move a readiness stage to pass. Three non-negotiables:
This adapter is not the owner of generic dbt competence. Model-authoring advice, generic test design, command syntax, documentation lookup, MCP configuration, and troubleshooting belong to the official dbt Labs agent skills and dbt MCP. Official-skill activation and discovery must be proven by the Spec 148 harness probe before routing to those skills; MCP liveness remains a separate preflight fact. This skill owns only Seshat's governed pre-gate, invocation policy, evidence normalization, parity interpretation, and human-stop seams around the official dbt Core executor; it must not reproduce upstream instructions.
- The entry gate is the FIRST refusal point (Principle IV). The canonical gate
signal is
mappings/<table>/readiness-status.yaml->stages.mapping_ready.status == passWITH a matchingapprovals[]entry (RS1); its human-readable mirrorunresolved-questions.mdGate status: CLEARED(zero open rows) MUST agree. dbt may run NO staging/silver/gold model unless that canonical signal holds -- a missing readiness-status file,mapping_ready != pass, or a mismatch between the two -> Refuse + record ablocking_reason. The presence of dbt model files is NOT permission to build. - A green
dbt testis EVIDENCE, never an approval (the governance hinge). Record the pass/fail counts asevidence[]/blocking_reasons[]; Tower readiness + a named human move Silver/Gold Ready topass, citing that evidence + the approval. There is NO path by which a green run alone writespass. - dbt stops at gold (Principle III). dbt is
DB-connected, not publish-capable; materializing/publishing a Power BI model is the parked F016 adapter, gated separately.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 146 lines · 142 tokens per session scan A f59dea095fa1
dbt-transformation-adapter is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 142 tokens to every session and 2,398 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
metricflow_ingest
Map a MetricFlow semanticmodel or metric into ktx semantic layer sources. Covers the MetricFlow to ktx primitive table, extends: inheritance flattening, metric-type handling (simple / derived / ratio / cumulative / conversion), model: ref('x') resolution, and four worked examples. Load when the turn contains…
lookml_ingest
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derivedtable, standalone with sqlalwayswhere). Load when the turn contains .lkml content.
sigma_ingest
Extract durable ktx wiki knowledge from staged Sigma data model specs and workbook summaries. Load for WorkUnits with unitKey sigma-data-models or sigma-workbooks.
modeler
Build, validate, and manage semantic models using Sidemantic. Use when asked to create a semantic layer, define metrics/dimensions, model a database schema, generate models from SQL queries, import from Cube/dbt/LookML, or set up analytics definitions. Prioritizes CLI-first workflows, with YAML and optional Python API…
powerbi-data-catalog-lineage
Data catalog and lineage management. Use when the user mentions: data catalog, lineage, data governance, Microsoft Purview, data dictionary, metadata, data discovery, impact analysis, endorsement, certified, promoted, scan, data map, business glossary, column-level lineage, table lineage, sensitivity label, data…
powerbi-medallion-architecture
Bronze/Silver/Gold lakehouse design. Use when the user mentions: medallion, bronze, silver, gold, lakehouse, data lake, data architecture, layer design, raw layer, curated layer, semantic layer, OneLake.